Issue 600362: Relocated parse_qs() and parse_qsl(), from the cgi module

to the urlparse one.  Added a PendingDeprecationWarning in the old
module, it will be deprecated in the future.  Docs and tests updated.

1 files changed, 87 insertions, 1 deletions

diff --git a/Lib/urlparse.py b/Lib/urlparse.py
index 1914304..c56d883 100644
--- a/Lib/urlparse.py
+++ b/Lib/urlparse.py
@@ -5,7 +5,7 @@ UC Irvine, June 1995.
 """
 
 __all__ = ["urlparse", "urlunparse", "urljoin", "urldefrag",
-           "urlsplit", "urlunsplit"]
+           "urlsplit", "urlunsplit", "parse_qs", "parse_qsl"]
 
 # A classification of schemes ('' means apply by default)
 uses_relative = ['ftp', 'http', 'gopher', 'nntp', 'imap',
@@ -267,6 +267,92 @@ def urldefrag(url):
     else:
         return url, ''
 
+# unquote method for parse_qs and parse_qsl
+# Cannot use directly from urllib as it would create circular reference.
+# urllib uses urlparse methods ( urljoin)
+
+_hextochr = dict(('%02x' % i, chr(i)) for i in range(256))
+_hextochr.update(('%02X' % i, chr(i)) for i in range(256))
+
+def unquote(s):
+    """unquote('abc%20def') -> 'abc def'."""
+    res = s.split('%')
+    for i in xrange(1, len(res)):
+        item = res[i]
+        try:
+            res[i] = _hextochr[item[:2]] + item[2:]
+        except KeyError:
+            res[i] = '%' + item
+        except UnicodeDecodeError:
+            res[i] = unichr(int(item[:2], 16)) + item[2:]
+    return "".join(res)
+
+def parse_qs(qs, keep_blank_values=0, strict_parsing=0):
+    """Parse a query given as a string argument.
+
+        Arguments:
+
+        qs: URL-encoded query string to be parsed
+
+        keep_blank_values: flag indicating whether blank values in
+            URL encoded queries should be treated as blank strings.
+            A true value indicates that blanks should be retained as
+            blank strings.  The default false value indicates that
+            blank values are to be ignored and treated as if they were
+            not included.
+
+        strict_parsing: flag indicating what to do with parsing errors.
+            If false (the default), errors are silently ignored.
+            If true, errors raise a ValueError exception.
+    """
+    dict = {}
+    for name, value in parse_qsl(qs, keep_blank_values, strict_parsing):
+        if name in dict:
+            dict[name].append(value)
+        else:
+            dict[name] = [value]
+    return dict
+
+def parse_qsl(qs, keep_blank_values=0, strict_parsing=0):
+    """Parse a query given as a string argument.
+
+    Arguments:
+
+    qs: URL-encoded query string to be parsed
+
+    keep_blank_values: flag indicating whether blank values in
+        URL encoded queries should be treated as blank strings.  A
+        true value indicates that blanks should be retained as blank
+        strings.  The default false value indicates that blank values
+        are to be ignored and treated as if they were  not included.
+
+    strict_parsing: flag indicating what to do with parsing errors. If
+        false (the default), errors are silently ignored. If true,
+        errors raise a ValueError exception.
+
+    Returns a list, as G-d intended.
+    """
+    pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
+    r = []
+    for name_value in pairs:
+        if not name_value and not strict_parsing:
+            continue
+        nv = name_value.split('=', 1)
+        if len(nv) != 2:
+            if strict_parsing:
+                raise ValueError, "bad query field: %r" % (name_value,)
+            # Handle case of a control-name with no equal sign
+            if keep_blank_values:
+                nv.append('')
+            else:
+                continue
+        if len(nv[1]) or keep_blank_values:
+            name = unquote(nv[0].replace('+', ' '))
+            value = unquote(nv[1].replace('+', ' '))
+            r.append((name, value))
+
+    return r
+
 
 test_input = """
       http://a/b/c/d